© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2061
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and their definitions or references in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical or specialized terminology, with a focus on academic or professional language.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.64
    сылкі
    -0.63
     snippetHide
    -0.57
    UpInside
    -0.54
     linkovi
    -0.54
     nahilalakip
    -0.54
    eaway
    -0.51
    EndInit
    -0.51
    ViewInit
    -0.50
    تفصیلات
    -0.50
    POSITIVE LOGITS
     term
    0.67
     terms
    0.65
     phrases
    0.63
     words
    0.63
     terminology
    0.61
     word
    0.59
     vocabulary
    0.59
     Begriffe
    0.59
     phrase
    0.56
     términos
    0.55
    Activations Density 0.205%

    No Known Activations